Instructions to use thanushtph/kannada-codet5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thanushtph/kannada-codet5 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="thanushtph/kannada-codet5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("thanushtph/kannada-codet5")
model = AutoModelForSeq2SeqLM.from_pretrained("thanushtph/kannada-codet5")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use thanushtph/kannada-codet5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thanushtph/kannada-codet5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thanushtph/kannada-codet5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/thanushtph/kannada-codet5

SGLang

How to use thanushtph/kannada-codet5 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "thanushtph/kannada-codet5" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thanushtph/kannada-codet5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "thanushtph/kannada-codet5" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thanushtph/kannada-codet5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use thanushtph/kannada-codet5 with Docker Model Runner:
```
docker model run hf.co/thanushtph/kannada-codet5
```

thanushtph commited on Dec 17, 2025

Commit

64d5e94

verified ·

1 Parent(s): f036a1d

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +27 -0

README.md ADDED Viewed

	@@ -0,0 +1,27 @@

+---
+pipeline_tag: text2text-generation
+library_name: transformers
+language: kn
+---
+# Kannada CodeT5
+This repository hosts a Kannada CodeT5 model fine-tuned for code-related text generation.
+## Inference
+```python
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+model_id = "thanushtph/kannada-codet5"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
+inputs = tokenizer("translate code to Kannada", return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=64)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+Once uploaded, the Hugging Face Inference API can be called via:
+- POST https://api-inference.huggingface.co/models/thanushtph/kannada-codet5